/ Annuaire / Playground / wikipedia-mcp
● Communauté Rudra-ravi ⚡ Instantané

wikipedia-mcp

par Rudra-ravi · Rudra-ravi/wikipedia-mcp

Ground Claude's answers in Wikipedia — search, full articles, summaries, sections, links, coordinates — with multi-language and locale-aware variants.

wikipedia-mcp exposes 10+ tools over the Wikipedia API. Go beyond what Claude 'remembers' with authoritative, up-to-date article content, handle Chinese traditional/simplified variants, and use locale codes instead of language codes for clarity.

Pourquoi l'utiliser

Fonctionnalités clés

Démo en direct

Aperçu en pratique

wikipedia.replay ▶ prêt
0/0

Installer

Choisissez votre client

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "wikipedia": {
      "command": "uvx",
      "args": [
        "wikipedia-mcp"
      ],
      "_inferred": true
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "wikipedia": {
      "command": "uvx",
      "args": [
        "wikipedia-mcp"
      ],
      "_inferred": true
    }
  }
}

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "wikipedia": {
      "command": "uvx",
      "args": [
        "wikipedia-mcp"
      ],
      "_inferred": true
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "wikipedia": {
      "command": "uvx",
      "args": [
        "wikipedia-mcp"
      ],
      "_inferred": true
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "wikipedia",
      "command": "uvx",
      "args": [
        "wikipedia-mcp"
      ]
    }
  ]
}

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json
{
  "context_servers": {
    "wikipedia": {
      "command": {
        "path": "uvx",
        "args": [
          "wikipedia-mcp"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

claude mcp add wikipedia -- uvx wikipedia-mcp

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : wikipedia-mcp

Cite Wikipedia instead of relying on model memory

👤 Anyone doing research-style Q&A ⏱ ~2 min beginner

Quand l'utiliser : The model's training cutoff is older than the facts you need (new events, refreshed biographies, updated stats).

Déroulement
  1. Ask with citation requirement
    When did the 2026 Winter Olympics happen and where? Use the wikipedia MCP and cite the article.✓ Copié
    → Answer + Wikipedia article title/URL

Résultat : Answers with a verifiable source, less hallucination.

Pièges
  • Wikipedia itself has errors / vandalism — For high-stakes facts, cross-check with a second source

Build a one-page dossier on a person or topic

👤 Journalists, prep-for-meeting folks ⏱ ~10 min beginner

Quand l'utiliser : You're meeting someone unfamiliar or writing about a new-to-you topic and want structured context fast.

Déroulement
  1. Summary first
    Get a summary of [person/topic] from Wikipedia. Then list sections so I can pick which to deep-read.✓ Copié
    → Summary + TOC
  2. Pull the key sections
    Give me full text of the 'Career' and 'Controversies' sections.✓ Copié
    → Section text
  3. Related threads
    What related Wikipedia topics should I also skim?✓ Copié
    → Related topic list with 1-line summaries

Résultat : 10-minute dossier better than ad-hoc googling.

Pièges
  • Wikipedia page doesn't exist for the person — Fall back to web search (firecrawl) for less-covered subjects
Combiner avec : notion

Compare how a topic is covered across languages

👤 Researchers, translators, international ops ⏱ ~15 min intermediate

Quand l'utiliser : You suspect the English and Chinese Wikipedia articles on a topic differ materially (they often do for geopolitical topics).

Déroulement
  1. Pull both versions
    Get Wikipedia articles on [topic] in English and Simplified Chinese (zh-Hans).✓ Copié
    → Two article bodies
  2. Diff the framing
    What facts are in one but not the other? How does each frame the controversy?✓ Copié
    → Structured comparison

Résultat : Nuanced multi-perspective understanding.

Pièges
  • Translation quality varies — Ask Claude to quote original language too for contested phrasings

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

wikipedia + notion

Build a 'places visited' Notion DB with Wikipedia summaries

For each row in my 'Trips' Notion DB, fetch the Wikipedia summary of the destination city and populate the 'About' column.✓ Copié
wikipedia + google-map

Show a topic on a map

Get coordinates of these 10 battles from Wikipedia; render them on a static Google map.✓ Copié

Outils

Ce que ce MCP expose

OutilEntréesQuand appelerCoût
search_wikipedia query: str, language?: str, limit?: int Find candidate articles free
get_article title: str, language?: str Need full content; use summary if 2-3 sentences suffice free
get_summary title, language? Quick context without full article cost free
get_sections title, language? Decide which sections to pull before pulling full article free
get_section title, section, language? Cheaper than full article when you know what you want free
get_links title, language? Discover related articles free
get_coordinates title Plot an article's place on a map free
get_related_topics title Research-mode expansion free

Coût et limites

Coût d'exécution

Quota d'API
Wikipedia rate limits: ~200 requests/sec from an IP; add delays for long scripts
Tokens par appel
Full articles 2k-15k tokens; summaries 200-500
Monétaire
Free
Astuce
Always start with get_summary or get_sections — avoid pulling a whole get_article unless you need the full text.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : Optional Wikimedia OAuth token for higher rate limits
Sortie de données : Outbound to Wikipedia's servers only

Dépannage

Erreurs courantes et correctifs

403 Forbidden on heavy use

Anonymous rate limit hit. Provide a personal access token or slow down (add sleep).

Page not found

Titles are case-sensitive and disambiguation-specific. Use search_wikipedia first to get the canonical title.

Chinese article returns Traditional when I want Simplified

Pass language=zh-Hans or language=zh-Hant explicitly.

Alternatives

wikipedia-mcp vs autres

AlternativeQuand l'utiliserCompromis
DBpedia / Wikidata MCPYou want structured data (infobox fields) rather than proseBetter for querying facts; worse for reading
Direct Wikipedia API via fetch MCPYou need maximum controlYou parse the JSON yourself

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills